---
title: sa
emoji: 📈
colorFrom: indigo
colorTo: pink
sdk: gradio
sdk_version: 4.25.0
app_file: app.py
pinned: false
license: mit
---

**Title: Sentiment Analysis with RoBERTa**

This project deploys a sentiment analysis model leveraging a fine-tuned RoBERTa model from CardiffNLP, designed to predict the sentiment of tweets or any short texts. The model categorizes texts into sentiments like positive, negative, and neutral. It is deployed with a Gradio interface for easy user interaction.

**Model Details:**

The model `cardiffnlp/twitter-roberta-base-sentiment-latest` is used, which is fine-tuned for sentiment analysis on tweets. It's based on the RoBERTa base architecture, a highly effective transformer model.

**Features:**

- Preprocesses text to handle specific features like mentions and URLs in tweets.
- Predicts sentiment, providing scores for categories (positive, negative, neutral).
- Offers a user-friendly web interface through Gradio for quick predictions.

**Installation:**

Ensure Python 3.6 or newer is installed. Install the required libraries with the following command:

```bash
pip install gradio transformers numpy scipy
```

**Usage:**

To run the application:

1. Clone or download this repository to your local machine.
2. Open a terminal and navigate to the project directory.
3. Execute the application by running:

```bash
python app.py
```

4. A Gradio interface will open in your default web browser for you to interact with the model.
```bash
Running on local URL:  http://127.0.0.1:7860
```

## Author

- [Lucian BLETAN](https://github.com/exaluc)